Large Language Models (LLMs) have become pervasive in everyday life, yet their inner workings remain opaque. While scholarly efforts have demonstrated LLMs' propensity to reproduce biases in their training data, they have primarily focused on the association of social groups with stereotypic attributes. In this paper, we extend this line of inquiry to investigate a bias akin to the social-psychological phenomenon where socially dominant groups are perceived to be less homogeneous than socially subordinate groups as it is reproduced by LLMs. We had ChatGPT, a state-of-the-art LLM, generate a diversity of texts about intersectional group identities and compared text homogeneity. We consistently find that LLMs portray African, Asian, and Hispanic Americans as more homogeneous than White Americans. They also portray women as more homogeneous than men, but these differences are small. Finally, we find that the effect of gender differs across racial/ethnic groups such that the effect of gender is consistent within African and Hispanic Americans but not within Asian and White Americans. We speculate possible sources of this bias in LLMs and posit that the bias has the potential to amplify biases in future LLM training and to reinforce stereotypes.

翻译：大型语言模型（LLMs）已深入日常生活，但其内部机制仍不透明。尽管学术界已证实LLMs会复现训练数据中的偏见，但现有研究主要聚焦于社会群体与刻板属性之间的关联。本文将研究拓展至社会心理学现象：LLMs可能复现一种偏见——即社会优势群体相较于从属群体被感知为更具异质性。我们让前沿大语言模型ChatGPT生成关于交叉群体身份的多样化文本，并比较文本同质性。结果一致发现：LLMs将非裔、亚裔及西班牙裔美国人描述得比白人美国人更具同质性；将女性描述得比男性更具同质性（但差异较小）。此外，性别效应在不同种族/族群中存在差异：非裔和西班牙裔美国人群体中性别效应具有一致性，但在亚裔和白人群体中则不显著。我们推测了LLMs产生这种偏见的潜在来源，并指出该偏见可能放大未来LLM训练中的偏差，同时强化刻板印象。